curl -X POST 'https://api.openai.com/v1/audio/voices' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "type": "prompt",
  "name": "example-name",
  "prompt": "example-prompt"
}'

# POST /audio/voices (OpenAI API)
Base URL: https://api.openai.com/v1
Auth: Authorization; OpenAI API key; required.
Request formats: application/json, multipart/form-data.
Last verified: 2026-10-20

> Create voice

## Critical Gotchas
* The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.
* Audio transcription uploads use multipart form data rather than a JSON request body.

## cURL
curl -X POST 'https://api.openai.com/v1/audio/voices' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "type": "prompt",
  "name": "example-name",
  "prompt": "example-prompt"
}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| type | body | string | Yes | Set to `prompt` to create a voice from a text description. |
| name | body | string | Yes | The name of the new voice. |
| prompt | body | string | Yes | A description of the desired voice. Must not contain only whitespace. |
| script_hint | body | string | No | Optional text for the voice to speak during creation. If omitted, a script is... |
| model | body | string | No | The voice creation model to use. Defaults to `auto`. |

## Response example
{"object":"audio.voice","id":"string"}

---
Need an API key? Get one at https://platform.openai.com/api-keys

POST

POST /audio/voices — OpenAI API

OpenAI API key (required); https://api.openai.com/v1

OpenAI API

Create voice

Base URL: https://api.openai.com/v1
Auth: Authorization: Bearer <OPENAI_API_KEY>
Last verified: 2026-10-20 · upstream hash matched

Actions Try in browser→

Agents: curl -H "Accept: text/markdown" this URL
→ 293 tokens · Vary: Accept

Critical gotchas

The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.

Audio transcription uploads use multipart form data rather than a JSON request body.

cURL

curl -X POST 'https://api.openai.com/v1/audio/voices' \  -H "Authorization: Bearer $OPENAI_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "type": "prompt",  "name": "example-name",  "prompt": "example-prompt"}'

Parameters

Name	In	Type	Required	Description
type	body	string	Yes	Set to `prompt` to create a voice from a text description.
name	body	string	Yes	The name of the new voice.
prompt	body	string	Yes	A description of the desired voice. Must not contain only whitespace.
script_hint	body	string	No	Optional text for the voice to speak during creation. If omitted, a script is generated from the prompt. Must not be blank after trimming whitespace; scripts that are too short are rejected.
model	body	string	No	The voice creation model to use. Defaults to `auto`.

Response 200 OK

{
  "object": "audio.voice",
  "id": "string",
  "type": "audio_sample",
  "prompt": "string",
  "name": "string",
  "created_at": 0
}

Get a free OpenAI API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.